关于「截止之前:泊松到达、二项受众与速率不确定下的达标概率」,《保证合约与预售成团》给出的定量结论是什么?

结论:第三章计算截止前的达标概率:预期订单恰等于门槛时只有 0.5133。

数据口径:书中参数为示意;全部计算由书中程序生成。

English version

对照数据表

下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库与结论吻合的打印值: 0.5133

threshold K100; audience for binomial M = 2000
expected total P(made) Poisson P(made) binomial
800.0171 0.0153
900.1582 0.1528
1000.5133 0.5143
1100.8417 0.8488
1200.9721 0.9757
1300.9972 0.9979
expected total needed for a target chance (Poisson):
target 0.80: mu108.4 = K x 1.084
target 0.90: mu113.1 = K x 1.131
target 0.95: mu117.0 = K x 1.170
target 0.99: mu124.8 = K x 1.248
查看完整验算程序
# Chapter 3. p31: the chance that a pre-sale reaches threshold K before
# its deadline when orders arrive as a Poisson process (expected total
# mu = rate x days) or come from a known audience of M people who each
# order with chance mu / M (binomial). Exact tails, summed with fsum
# in log space. Also: the expected total needed for a target chance.
# Illustrative: K = 100 orders, audience M = 2000.
import math

K, M = 100, 2000


def pois_tail(k, mu):
    # P(N >= k) = 1 - P(N <= k - 1)
    terms = [math.exp(j * math.log(mu) - mu - math.lgamma(j + 1))
             for j in range(k)]
    return 1.0 - math.fsum(terms)


def binom_tail(k, n, p):
    lp, lq = math.log(p), math.log(1 - p)
    terms = [math.exp(math.lgamma(n + 1) - math.lgamma(j + 1)
                      - math.lgamma(n - j + 1) + j * lp + (n - j) * lq)
             for j in range(k)]
    return 1.0 - math.fsum(terms)


def need(k, target):
    mu = float(k)
    while pois_tail(k, mu) < target:
        mu = round(mu + 0.1, 1)
    return mu


if __name__ == "__main__":
    print("threshold K = {}; audience for binomial M = {}".format(K, M))
    print("expected total   P(made) Poisson   P(made) binomial")
    for mu in (80, 90, 100, 110, 120, 130):
        print("{:14d}   {:15.4f}   {:16.4f}".format(
            mu, pois_tail(K, mu), binom_tail(K, M, mu / M)))
    print("expected total needed for a target chance (Poisson):")
    for t in (0.80, 0.90, 0.95, 0.99):
        mu = need(K, t)
        print("  target {:.2f}: mu = {:.1f}  = K x {:.3f}".format(
            t, mu, mu / K))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《保证合约预售成团阈值、退款承诺与公共品搭便车均衡母典》第 3 章「截止之前:泊松到达、二项受众与速率不确定下的达标概率」(版本 1.0.0). 5D Library. DOI 待发布

DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-316 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026316,
  author    = {Fan, Yafu},
  title     = {Assurance Contracts and Pre-Sale Group Thresholds: Refund Promises and Free-Riding Equilibria in Public Goods},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论